Although transformer-based Neural Language Models demonstrate impressive
performance on a variety of tasks, their generalization abilities are not well
understood. They have been shown to perform strongly on subject-verb number
agreement in a wide array of settings, suggesting that they learned to track
syntactic dependencies during their training even without explicit supervision.
In this paper, we examine the extent to which BERT is able to perform
lexically-independent subject-verb number agreement (NA) on targeted syntactic
templates. To do so, we disrupt the lexical patterns found in naturally
occurring stimuli for each targeted structure in a novel fine-grained analysis
of BERT's behavior. Our results on nonce sentences suggest that the model
generalizes well for simple templates, but fails to perform
lexically-independent syntactic generalization when as little as one attractor
is present.

该研究评估了基于 Transformer 的神经语言模型在语法识别任务中的一般性能力，特别是在处理句子结构和词汇形态方面的通用表现，描述了在有吸引因素的情况下，词汇独立的句法泛化失败的情况。

BERT 是否真的赞同？对语法任务上词汇依赖的精细分析

Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task

LSTM-based recurrent neural networks are the state-of-the-art for many
natural language processing (NLP) tasks. Despite their performance, it is
unclear whether, or how, LSTMs learn structural features of natural languages
such as subject-verb number agreement in English. Lacking this understanding,
the generality of LSTM performance on this task and their suitability for
related tasks remains uncertain. Further, errors cannot be properly attributed
to a lack of structural capability, training data omissions, or other
exceptional faults. We introduce *influence paths*, a causal account of
structural properties as carried by paths across gates and neurons of a
recurrent neural network. The approach refines the notion of influence (the
subject's grammatical number has influence on the grammatical number of the
subsequent verb) into a set of gate or neuron-level paths. The set localizes
and segments the concept (e.g., subject-verb agreement), its constituent
elements (e.g., the subject), and related or interfering elements (e.g.,
attractors). We exemplify the methodology on a widely-studied multi-layer LSTM
language model, demonstrating its accounting for subject-verb number agreement.
The results offer both a finer and a more complete view of an LSTM's handling
of this structural aspect of the English language than prior results based on
diagnostic classifiers and ablation.

本文引入了影响路径的概念，对 LSTM 网络中的语言结构特征进行了分析和研究，并精细化地定位和分段语言结构中的概念及其相关元素，从而更全面、准确地展现了 LSTM 网络处理英语语言结构方面的能力。